A Passion For 'Puters

I got a newsletter the other day that made me think (as I suppose is the purpose of most of these newsletters, right?). In it, Anne-Laure Le Cunff writes about using your voice to clarify and help produce thinking in ways that silent contemplation might not achieve. Essentially, she claims that talking to yourself helps you think clearly and understand what it is you are doing/what needs to be done more effectively than silent consideration of your to-do list or schedule. I’m all for talking to myself – I’m a pretty decent conversationalist when my audience is just me and I’ve begun doing this myself over the last few months for different purposes that I will attempt to codify and regularize in my daily routine. Mostly, what I’ve been doing is talking through my processes that I do irregularly or not very often (yearly, for example) so that I have a record of what it is I do when next I need to perform those processes. These range from setting up and managing a new director retreat for Kansas library directors to working through uploading new episodes of Ninjio to our LMS for our NEKLS librarians.

I use Tana to record and then transcribe those ramblings and I have a custom process that reads the transcription and pulls out enumerated steps for the process I’m describing as I do it. These steps are then used the next time I do that process to help me remember what it is I need to do – basically I’m self-documenting as I go.

However, I also tend to use voice memos when I’m otherwise busy (driving, walking, reading) to remember quick things and to set up future to-dos. On my way back from the Leadership Institute a couple of weeks ago, I dictated a few notes of things I wanted to remember and follow up on based on some coaching/mentoring conversations I’d had with a few of the fellows at the Institute. Those points were then transcribed to my Tana inbox, where I stuck a Task supertag on them and gave them a due date and they’ll pop back up in my daily calendar/to-do list on the appropriate date in a week or two.

Since reading Anne-Laure’s blog post about using your voice to help with thinking, however, I intend to do even more voice memos, process transcriptions, and general thinking aloud while my phone sits next to me, faithfully recording every um, uh, like, and so that I say (and I say those a lot – sorry about that to anyone who has to listen to me think aloud…). You might want to give it a try too – even if you don’t have a Tana subscription, many chatbots can transcribe voice (and some are purpose built for it, like Otter.ai) and give you a very good set of words to use in your work!

And yes, I did tap my Tana Capture voice memo button on the home screen of my phone and dictate in a “hey, write a blog post about voice capture and Anne-Laure’s newsletter” with some other thoughts about how the post might go. And those thoughts are now immortalized (ha!) on my blog for posterity… 😉

Just finished reading a book by Jenny Wood (Wild Courage) that suggests a technique for clarifying thought and producing a project plan quickly and efficiently called “pencil sharpening”. Her idea is that as you get an assignment or start on a project, you sit down in the first 24 hours and write out a one-page or so “plan of attack”. How will you start the work?, what are your metrics?, who will be important stakeholders?, how long will it take to do this work?, etc. As I was reading through her description of this technique she uses to get work off the ground, I was reminded of a sort of similar technique called Chair Flying.

Chair flying is something that some pilots do to prepare for flights. It involves visualization of the flight, essentially. You consider what you need to have when you take off, what kind of atmospheric conditions you might encounter, traffic at your end point airport, and so on. My version of chair flying is one of my first stops when I embark on a new project and it just involves me turning to my trusty pen and legal pad, writing the name of the project across the top and then visualizing what needs to happen to get to “success” at the end of the project. What kinds of info/materials/resources do I need? What sort of roadblocks might I encounter? What are my deliverables as I create the project and when might those be reasonably expected? I basically work through, in my head, what the project will entail and list out everything that pops into my head while I do that. I prefer to do this on paper, but there is no reason this couldn’t be done with Google Docs and a keyboard instead.

The same flexibility seems to be in place for pencil sharpening. Jenny says that she does it on a Google doc, but it can be done on paper if you’d like. I think that, despite the fact that I prefer to chair fly on paper, my first attempts at pencil sharpening will be on a Google Doc because I imagine that my doc that I come up with will be the heart of my project plan and it might as well be born digital because it will need to become digital at some point anyway.

Those two techniques, put together (have a chair flying section in your pencil sharpening document, even if you don’t actually refer to it as chair flying) would make for a really strong project plan right out of the gate – and the fact that the pencil sharpening doc is recommended to be produced in the first 24 hours after receiving the work/project helps to combat procrastination and that panicked feeling you get when you realize a big project is due in two days and you have hardly even started on it…

One of the classes I teach is a Library Support Staff Certification (LSSC) module on Technology for folks who are going for the certification. In the most recent class I taught, one that has just finished, I encountered a couple of different attitudes toward AI that I found interesting and wanted to explore in writing – so here we are.

First off, one person was uncomfortable with the use of copyrighted materials on AI training and wanted me to remove AI mentions from the assignment to find and discuss how emerging tech might be used in libraries in the future. My response is, as a published author with 5 copyrighted books to my name along with articles and contributed chapters and whatnot, that I really want people (for a wide definition of people in this case, I agree) to read and learn from what I write. It’s why I go to the trouble (it’s not for the money, trust me). I can’t see much difference in an AI ingesting my text to learn from and a library staffer checking my book out from their professional collection to learn from. Other than the couple of dollars in royalties I got from the library’s purchase of my book, I don’t see any material difference in who or what is making use of my writing in order to learn things.

That being said, I am one person with one take on the subject and there are numerous other, equally valid takes that can be had on this subject as well, so I’m definitely not speaking for all authors here! Just myself.

To be honest, while I’m less concerned about the copyright issue for myself, I am concerned about the environmental impact of all this computing power being put to the task of coming up with catchy titles for presentations… but I’m of the opinion that green energy is nearly unstoppable at this point, despite efforts being made in that direction, and we’ll eventually get the right balance of renewable energy sources and less energy-hungry chips. Again, just my personal belief, yours may differ.

So while AI is a thing that is happening in the world and, therefore, in libraries, one thing I’d like to see more of is strong AI policy around it’s use in our organizations. Most libraries seem to be holding off, but putting something in place now that at least puts boundaries around personally identifying information (PII) being uploaded to a chatbot or not using it as a substitute for a search engine without thoroughly checking sources or not editing whatever comes out of the black box thoroughly (see “white genocide in South Africa and Grok” for more info on that – https://www.nytimes.com/2025/05/17/opinion/grok-ai-musk-x-south-africa.html?unlocked_article_code=1.IU8.1ur3.ZoMkQPUgkZmz&smid=url-share for a gift article link).

Blanket prohibitions on its use (as Wikipedia endured in its early years) is not going to be useful or helpful for our patrons. They use it, we need to understand how to help them use it more effectively and SAFELY. Those patrons may find things like the Goblin Tools suite of tiny chatbot prompts that help do things like break down large “to-do” items into smaller steps or check the tone of a body of writing or help people estimate the time and work involved in doing something to be really useful and it is our job to help them find it and use it SAFELY.

I’m in the process of writing an AI policy for my classes – what isn’t allowed, what I won’t do with AI (grade or provide feedback, for example), and what might be useful ways to use AI in my particular classes (still ruminating on whether to add that bit in or not, to be honest) – to put in the syllabus so that we all start off with a common baseline of what is and isn’t appropriate for AI use in class. I strongly suggest libraries do the same – come up with some policies that will guide staff and patrons on how to best use this new technology without forbidding it entirely.

One of the things I’m trying to do is to create documentation of things I do rarely – once a month, quarter, year, etc. – for future Robin to appreciate. I think I’ve stumbled upon a reasonably easy way to do this that fits in with my work as I’m doing it. Right now, I’m working on setting up Tana (www.tana.inc) to manage projects and various other to-dos and it is a pretty powerful system that allows you to build upon it’s linked data/AI/daily notes sort of foundation to create what is essentially an application that you get to customize to fit your working style.

Currently, I am using Tana to manage a project that I do every year, setting up a retreat for new directors in Kansas to kick off our APPLE program for training new public library directors. We travel to a reasonably central spot in KS, spend 25 hours together (eating no fewer than 7 times during those hours – when the brain is being worked, it’s best to feed it!) and then head back to our respective libraries, full of new contacts and information and (hopefully) ready to tackle a year of learning how to be the best director you can be. It includes 4 meals, an overnight stay, a keynote address of a couple of hours, several information sessions on community awareness, library planning, board relations, library policy management, and more. All of this needs to be set up, planned for, budgeted, reserved, undertaken, and then paid for from our APPLE budget.

This year, as I start to work on any part of that group of tasks (most recently it was putting together an info packet for students to learn about the location we’d be staying at and the schedule for the event, among other things), I’ve been turning on Tana’s “live transcription” feature and talking through the process of what I’m doing out loud. Once the transcript is ready, I run a command that takes that transcript, runs it through an AI (ChatGPT to be precise) service to pull out the step-by-step procedures I’ve just narrated, and gives me a numbered list of steps that are needed to complete the task I just did. Those steps are added to the project node and I move on to the next task.

This is a very customized setup (but I’ve come to realize that all productivity setups have to be pretty custom or they just don’t work well) that involves specialized software and some knowledge of how to create commands and other bits and pieces of Tana functionality (though, of course, ChatGPT can be helpful there, too). That being said, it’s also the best way I’ve found of documenting what I do so that next year, I’ll have a list of steps contained within each task that I have to do to set up the APPLE 2026-27 retreat, based on what I did this year to make the APPLE 20205-26 retreat happen.

The biggest point of failure here is my ability to remember to turn on the live transcription service (a simple right click in the task on Tana, it’s not hard to do). I talk through what I’m doing half the time anyway, because I am my own favorite conversationalist… so that part is generally fine, but only if I turn on Tana’s ability to listen to my babbling. Once that transcript is done, the rest is pretty easy and automatic – start a command, transfer the transcript to it, copy the results into the task node and move on. Easy peasy. If you have all the building blocks.

That being said, this wouldn’t require using Tana and ChatGPT – it’s possible that you could use Google and NotebookLM or Gemini to get the same kind of functionality using the tools you are familiar with!

I was leading a chat on Project Management for the MPLA Chew and Chat program yesterday and we got to talking about analysis paralysis and technolust – 2 great ways to avoid doing actual work while feeling like you are getting things done. As an example of my technolust failing, I pointed the attendees to a “thing” that I had been playing with that morning. I took the content of my class lectures, workshop slides and other Project and Knowledge Management content that I had in my Google Drive, added it to a NotebookLM instance and then asked the Google AI to make a podcast out of the content.

The results are occasionally silly and it’s clear that the AI isn’t really sure about what is “lesson” and what is “example” in my workshops, but really, I’m nitpicking. The fact that the computer took about 3 minutes to review all of those resources – transcripts from nearly an hour of lectures + 6 or 7 slide decks – and came up with something that is actually sort of coherent is *mindblowing*. I include the podcast audio here so that you all can hear it – warts and all.

One thing to note – after the session, I got a note from a friend who was in the session who said that 2 of her staff attended and within minutes of the end of the session, had uploaded a database info sheet into a NotebookLM instance and produced a podcast that librarians in her state can use to learn about the state-offered databases (for as long as they continue to be offered, at least – there is some real threat that they’ll go away entirely in the next year or so in South Dakota, so if you live there, talk to your legislator!!). This all had nothing (really) to do with project management (other than the topic of my foray into techolusting) but it was one of those cool serendipitous moments that I felt I should share…

I read Building a Second Brain (BASB) a while back and got some great ideas from it (and read The Extended Mind as well, which is a great argument for why you need to spend some time on that second brain, both technologically and socially/environmentally), I believe, but I wanted to point out that there is a playlist on YouTube that takes the idea of progressive summarization and shows how it works, bit by bit. Tiago (author of BASB) shows how he takes notes on his Kindle app, moves them into Evernote, bolds them in one pass, then highlights the bolded stuff in a second pass, then takes the highlighted ideas and creates an outline from those ideas (he’s doing a book summary with a single source, but this can be extended to combining multiple sources of info pretty easily), then writes up his book summary, all while talking through his thought process while he’s doing it.

It’s a 3+ hour timesink, but I found it useful (especially the part where he takes his notes and creates an outline from them) to take the idea of processing your notes from something that you consume to something that you create. (I was about to make an analogy to how the body processes stuff, but then I considered what we create and I decided to spare you all ?)

Anyway, I skipped the shortest video (the one on moving your highlights from Kindle to Evernote) because I already have a process that takes my highlights from Readwise Reader, Kindle, and Medium and puts them into my favorite note-taking app (Tana, by way of the Readwise Obsidian Plugin – crazy manual process, but valuable!) and I really stopped paying attention in the outline to output video, because I have some experience doing that, too. The outline video, though, really gave me some great ideas on how to use the notes I have from my reading to help fuel my output here, at work, in my presentations and articles and in the classes I teach.

I have spent a little time asking ChatGPT questions, both work-related and personal (What elements are in a good security policy for libraries? Can you give me an outline for a class on knowledge management? What are the best places to visit in Louisville, KY?) and considering the answers I got (a reasonable list of things to include in library security policies and a good start to a “rubric” to evaluate policies as I am asked to comment on them at work but zero sources to tell me where the info comes from, a nice collection of topics to consider for a KM class but zero sources to tell me where the info comes from, and a pretty nice list of tourist traps in Louisville but zero sources to tell me where the info comes from). Not sure if you all caught the issues I might have with ChatGPT… I couldn’t figure out at all where the info comes from, but I was pretty happy with the results that I got from what seemed to me to be the process I’d have used (search for policies, collect various elements, produce the rubric from all those elements, etc.) but in 30 seconds, not 3 hours.

Yesterday, Google opened Bard up to folks on their waitlist and I got a chance to start futzing with it. The first thing I noticed is that in response to the same sort of questions that I’d asked ChatGPT earlier is that Bard gave me a source. A single source which brought up the question of how this was better than a search I could have done on my own, but a source was provided. My second question was to give me an outline for an essay on using soft skills at work and it gave me 3 “drafts” of the outline that I could use, but no sources this time.

I’ve not played with the Bing AI chatbot yet, but in one of the 15 trillion (not misinformation, just a slight exaggeration for effect) articles I’ve read in the past few weeks and months on the AI landscape, someone mentioned that Bing was “extensively footnoted”, which makes me think it might do a better job of citing it’s sources (I’m a bit hung up on this, maybe, but I’m a librarian and that’s a hazard of my profession).

Overall, I’m interested in the product of these chatbots and the idea that it can do some of the grunt work of finding, synthesizing and producing information that I do now by hand (and at great effort!!) giving me the opportunity to concentrate on providing value around the information it gives me and being able to make value judgements about what information to include. This would be easier to do if it was better at citing sources – but as the offerings mature and get more features and capabilities, it’s worth keeping an eye on at the least.

Part 1 – Capture | Part 2 – Manage | Part 3 – Connect | Part 4 – Enhance | Part 5 – Find | Part 6 – Create

Create

So, now that you have all this stuff that you might want to think about later and that you can use, remix and reconsider in order to create new things, what are you going to create? There are a number of articles on the web talking about how to take your Roam/Obsidian/Evernote/etc. notes and create content from them. Roam, as an outliner, has a particular number of those kinds of articles and videos available. I’ve tried using some of the techniques (I’m still really fascinated by the Archipelago of Ideas from the Building A Second Brain book where you take your outlined bullets about a topic and put them together in a separate note to create a document/video/script/whatever from them as those notes suggest a structure and a path for your argument) and they work to varying degrees of success for me. I still do best (for now) with creating content in the WordPress editing window (with my Roam graph and Evernote app and maybe a mind map or two open on my second monitor to support my work) as I’ve done for this entire series. If I’m writing something more formal, an article to be published or something like that, I use GDocs to create the content (again, with lots of apps open to support my work, including Zotero in this case).

I also use these tools to create tutorial videos for work and documentation for our catalog and various other library-related functions as well. This particular part of KM is likely my weakest. I’m pretty good at consuming and processing information, but the output of original work from those ideas is still in a nascent stage – it’s a work in progress.

That being said, there is a conversation going on (in the networked thought mode) through Twitter and other websites about the concept of a digital garden that is a support for us as we learn in public. The idea that blogging with its chronological, polished (ha!), and “finished” articles that are never revisited as you learn more is old and busted is making the rounds. Obviously, I have a soft spot for blogs as they are how I communicated in my early Internet days, but I’m becoming more and more interested in maybe starting up a digital garden of my own (though my thumb is as black as can be – I have been known to ask people what their plants did to get the death penalty if they are given to me as a gift…), but I’m still kicking that idea around a bit. I do like the idea of learning in public – I’ve often posted to the NEKLS Facebook page about classes I’m taking at work and what my homework assignments are so that the NEKLS librarians can learn along with me. It’s generally been well received, so I have some good experiences with it, I’ve just never really done it in any kind of systematic way. Maybe I’ll give it a try sometime. Stay tuned…

Part 1 – Capture | Part 2 – Manage | Part 3 – Connect | Part 4 – Enhance | Part 5 – Find | Part 6 – Create